Skip to main content
Glama

Server Details

Product search for AI shopping agents: prices and buy links from big retailers. No key needed.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 8 tools

Disambiguation4/5

The set deliberately ships two near-duplicate pairs: search_products/live_search and check_product_link/live_check. The descriptions make the split explicit (free cached vs paid live, monthly allowance vs x402 metering), so an agent can choose correctly, but the boundaries are only clear because of prose, not the tool surface itself. find_retailers, list_gaps, report_not_found and get_setup_and_upgrade_links are cleanly distinct.

Naming Consistency4/5

All names are snake_case and most are verb_noun (check_product_link, find_retailers, list_gaps, report_not_found, search_products). The two paid mirrors use a noun-first 'live_' prefix and get_setup_and_upgrade_links is an outlier in length, but nothing is camelCase or chaotic.

Tool Count4/5

Eight tools is a good scope for a niche product-search server, and each has a clear role. The count is slightly inflated by the two free/paid mirror pairs, which could arguably be one tool each with a mode flag.

Completeness5/5

The lifecycle is well covered: discovery (search_products, live_search), fallback retailer discovery (find_retailers), verification of a specific listing (check_product_link, live_check), and feedback loops (report_not_found, list_gaps), plus onboarding (get_setup_and_upgrade_links). No obvious dead ends for a shopping-lookup domain.

Available Tools

8 tools
find_retailersFind retailer search linksA
Read-onlyIdempotent
Inspect

Find which big retailers and brand stores to search for a product, with a ready-made search link for each. Use this when search_products returns nothing, when the shopper names a store or brand, or to give the shopper places to look. Returns up to 10 retailers (the brand's own store first, then category specialists, then general retailers), each with search_url, a short reason, and agent_access ('open' = you can fetch the page, 'blocks_bots' = hand the link to the shopper). No key needed. Example: {"query": "breville espresso machine", "region": "AU"}.

Inputs: query (required), limit, region. Returns: retailers, categories

list_gapsList product gapsA
Read-onlyIdempotent
Inspect

Products people asked for that none of the closest products checked offer, with the original ask, requirements and products checked, plus agent-search misses repeated by 3+ requests from 2+ agents. No key: 10-gap preview. With a free key (POST /v1/keys): full rows, paged by cursor, counts 1 call. A gap is worth a closer look, never verified demand.

Inputs: q, limit, cursor. Returns: code, gaps, agent_gaps, next_cursor, +3 more

live_checkCheck one product page now (paid, no quota)A
Read-onlyIdempotent
Inspect

Paid: US$0.005 per call in USDC over x402 (or 5 prepaid credits), with no monthly quota. Fetch one retailer product page now and return whether it still exists, its current price and stock. Not charged if the page could not be read. Without payment the result is an x402 payment request; attach the signed payment at _meta["x402/payment"] and call again. check_product_link does the same within the free monthly allowance.

Inputs: url (required).

report_not_foundReport unsatisfied shopping requestAInspect

Free. Report a genuine shopper mismatch after a search. Do not send synthetic reports or personal details. Response states whether the agent observation was saved; it is not verified human demand.

Inputs: query (required). Returns: code, note, saved, evidence

search_productsSearch retail productsA
Read-onlyIdempotent
Inspect

Search products for sale at big retailers and well-known brand stores: Myer, JB Hi-Fi, Zappos, Nike and about 180 more, deepest in Australia and US fashion. Use this when a shopper wants a product, a price check, or somewhere to buy it. Put the product in query (2 to 4 words, brand first: 'sony headphones', 'breville espresso machine') and budget, country, size and colour in their own fields. Returns ranked listings with title, store, price, availability, the retailer's product url and when it was last checked, plus retailer_search links to try when nothing matches. Prices are in each listing's own currency, exclude shipping and tax, and are not converted. No key needed. Example: {"query": "espresso machine", "country": "AU", "max_price": 600}.

Inputs: query (required), need, size, sort, +8 more. Returns: code, note, count, found, +4 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Real Amazon (US, UK, DE, CA, AU) & Walmart shopping data for AI assistants: ranked product shortlists, current prices, live stock, real ratings, and price/BSR history from a 17M+ product warehouse. Free hosted endpoint, no signup — 30 queries a day.
      2
      18
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources